]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/heise.py
d/p/remove-autoupdate-mechanism.patch: Update patch with metadata at the top.
[youtubedl] / youtube_dl / extractor / heise.py
index 382f32771db513fc1c41e81f14ce42308ad50276..8f49f52efd5398abbc7b922b9e2a268b3f609e2a 100644 (file)
@@ -2,10 +2,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .kaltura import KalturaIE
+from .youtube import YoutubeIE
 from ..utils import (
     determine_ext,
     int_or_none,
     parse_iso8601,
 from ..utils import (
     determine_ext,
     int_or_none,
     parse_iso8601,
+    smuggle_url,
     xpath_text,
 )
 
     xpath_text,
 )
 
@@ -25,6 +28,35 @@ class HeiseIE(InfoExtractor):
             'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
             'thumbnail': r're:^https?://.*/gallery/$',
         }
             'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
             'thumbnail': r're:^https?://.*/gallery/$',
         }
+    }, {
+        # YouTube embed
+        'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
+        'md5': 'e403d2b43fea8e405e88e3f8623909f1',
+        'info_dict': {
+            'id': '6kmWbXleKW4',
+            'ext': 'mp4',
+            'title': 'NEU IM SEPTEMBER | Netflix',
+            'description': 'md5:2131f3c7525e540d5fd841de938bd452',
+            'upload_date': '20170830',
+            'uploader': 'Netflix Deutschland, Österreich und Schweiz',
+            'uploader_id': 'netflixdach',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.heise.de/video/artikel/nachgehakt-Wie-sichert-das-c-t-Tool-Restric-tor-Windows-10-ab-3700244.html',
+        'md5': '4b58058b46625bdbd841fc2804df95fc',
+        'info_dict': {
+            'id': '1_ntrmio2s',
+            'timestamp': 1512470717,
+            'upload_date': '20171205',
+            'ext': 'mp4',
+            'title': 'ct10 nachgehakt hos restrictor',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
         'only_matching': True,
     }, {
         'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
         'only_matching': True,
@@ -40,19 +72,28 @@ class HeiseIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        title = self._html_search_meta('fulltitle', webpage, default=None)
+        if not title or title == "c't":
+            title = self._search_regex(
+                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
+                webpage, 'title')
+
+        yt_urls = YoutubeIE._extract_urls(webpage)
+        if yt_urls:
+            return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
+
+        kaltura_url = KalturaIE._extract_url(webpage)
+        if kaltura_url:
+            return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
+
         container_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
         container_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
+
         sequenz_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
             webpage, 'sequenz ID')
 
         sequenz_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
             webpage, 'sequenz ID')
 
-        title = self._html_search_meta('fulltitle', webpage, default=None)
-        if not title or title == "c't":
-            title = self._search_regex(
-                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
-                webpage, 'title')
-
         doc = self._download_xml(
             'http://www.heise.de/videout/feed', video_id, query={
                 'container': container_id,
         doc = self._download_xml(
             'http://www.heise.de/videout/feed', video_id, query={
                 'container': container_id,